Myopia Fight Gets an AI Upgrade: Early Detection and Prevention on the Horizon
The rising global prevalence of nearsightedness is prompting innovative solutions, and artificial intelligence emerges as a key player in the early detection and management of this vision issue. New research explores AI’s potential to revolutionize how we understand and treat myopia.
AI’s Role in Myopia Detection
Myopia, or nearsightedness, affects billions worldwide, potentially impacting education, careers, and overall quality of life. By 2050, nearly half of the global population could be myopic. Consequently, early diagnosis of myopia is critical to prevent vision damage. Drs. Li Li, Jifeng Yu, and Nan Liu, from the Department of Ophthalmology, Capital Medical University, China, published a study in Pediatric Investigation on March 18, 2025.
AI models trained via machine and deep learning can identify myopia from fundus photographs and optical coherence tomography images. Analyzing retinal patterns, AI can diagnose the condition. Self-monitoring tools like the SVOne handheld device use AI algorithms to detect eye defects and diagnose myopia by accessing an online image database. Furthermore, AI can detect behavioral changes, particularly in children, often overlooked.
Risk Assessment and Prediction
Machine learning methods, such as support vector machines, can identify myopia risk factors.
“An XGBoost-based model can be fed large quantities of longitudinal data, allowing it to learn the outcomes and associated risk factors of myopia in numerous patients. This, in turn, allows the model to assess the risk factors of new patients based on their genetics, family history, environment, and physiological parameters,” explains Dr. Li Li.
Predicting the progression of myopia allows for adjusting clinical approaches, shaping clinical practice, and policymaking. Training AI with extensive biometric data and images allows for predicting outcomes in new patients. According to the World Health Organization, uncorrected refractive errors like myopia are a leading cause of vision impairment globally; around 80% of visual impairment worldwide is avoidable or curable with treatment.
Challenges and Future Directions
Despite the promise of AI, several challenges remain. Accurate, high-quality datasets are essential to avoid biases. Models trained on data from large hospitals may not be representative of the broader patient population. Additionally, the need for a clinical basis for AI diagnoses and patient data privacy are important considerations.
An eye exam being performed on a child.
“While our study highlights the remarkable progress made in the clinical application of AI in myopia, further studies are needed to overcome the technological challenges. By building high-quality datasets, improving the model’s capacity to process multimodal image data, and improving human-computer interaction capability, the AI models can be further improved for widespread clinical application,” concludes Dr. Jifeng Yu.